A Custom Self-Learning ML + Computational Biology Curriculum

By

 


A Custom Self-Learning ML + Computational Biology Curriculum


Recently I've been toying with the idea of potentially forming a biotech startup one day. I've been seeing a lot of new startups recently that are leveraging bioinformatics, machine learning/AI, systems biology, and computational biology to construct new cellular/biological interfaces that have the potential to pave the way towards true precision medicine.

If precision medicine is actually achieved in its fullest capacity, then diseases like cancer can effectively be cured, becoming little more than a chronic condition that must be treated over time, rather than a life-threatening disease. And not just cancer, but many other diseases, like metabolic disorders and genetic disorders. I believe that this can be achieved in our lifetimes, or at least some time this century. But we'll see. 

When looking at all these companies doing this work, I kept thinking to myself that I wanted to learn this material for myself. Except that my university doesn't offer many classes in these niche subjects sadly. So, I searched the furthest reaches of the internet and assembled my own self-paced, self-learning curriculum that addresses these topics all using online and completely free resources (except for some of the books I have recommended, but even many of the books can be found online in pdf form). The curriculum makes use of MIT OpenCourseWare content as well as free online courses I was able to find from places like Harvard and Stanford.

Below, I have an outline of the curriculum with links to all the resources. If you would like to learn about these topics, I welcome you to use it for your own ML/computational biology education journey.

I hope you enjoy and thank you for reading!

Machine Learning for Computational Biology Curriculum 


Phase 1 - Setup and Foundations

Goal: ML Fundamentals

Courses:

Online Resources:

Books:

  • unchecked

    Hands-On Machine Learning (Geron) → Chapters 1 - 9

  • unchecked

    Designing Machine Learning Systems (Chip Huyen) → Part 1

  • unchecked

    Deep Learning with Python (Chollet) → Chapters 1 - 10



Phase 2 - Full Machine Learning Immersion

Goal: Learn specifics and advanced topics of ML

Courses:

Online Resources:

Books:





Phase 3 - Bioinformatics + R Training

Goal: Learn R, Bioconductor, workflows

Courses:

Online Resources:

Books:





Phase 4 - Systems Biology + Computational Biology

Goal: Become familiar with Systems Biology

Courses:

Books:

  • unchecked

    An Introduction to Systems Biology (Uri Alon)




Phase 5 - Precision Medicine and ML Applications to Cancer

Goal: Become familiar with specific techniques of ML used to analyze biological systems.

Courses:

Online Resources:

Books:




Phase 6 - MLOps and Scaling Up

Goal: Take ML to the industrial level

Courses:

Books:






Realistic Weekly Schedule


  • Monday: 1 hour (Lecture video + Notes)

  • Tuesday: 1 hour (Lecture video + Notes)

  • Wednesday: 1.5 hours (Book reading / theory review)

  • Thursday: 1 hour (Lecture video + Notes)

  • Friday: 1.5 hours (Work on coding project for given phase)

  • Saturday: 2 hours (Coding project / data pipelines)

  • Sunday: Off (write blog post about week?)





Timeline


Phase 1

Duration: 12 weeks

Weeks 1-4:

  • unchecked

    MIT 6.036 Lectures 1-13

Weeks 5-8:

  • unchecked

    Kaggle ML + DL

  • unchecked

    ML Google Crashcourse

  • unchecked

    Hands-On Machine Learning (Geron) → Chapters 1-9

Weeks 9-12:

  • unchecked

    FastAI Part I

  • unchecked

    Chollet Chapters 1-10

Phase 2

Duration: 12 weeks

Weeks 13-18:

Weeks 19-22:

Weeks 23-24




Phase 3

Duration: 16 weeks

Weeks 25-28:

Weeks 29-32:

Weeks 33-36:

Weeks 37-40 (Buffer Weeks)

  • unchecked

    Bioinformatics Data Skills (Buffalo) (Continued)

  • unchecked

    Catch up on any work/content that you might be behind in




Phase 4

Duration: 12 weeks

Weeks 41-46

Weeks 47-52




Phase 5

Duration: 12 weeks

Weeks 53-56

Weeks 57-60

Weeks 61-64




Phase 6

Duration: 8 weeks

Weeks 65-68

  • unchecked

    Made with ML

  • unchecked

    Read book: Designing Machine Learning Systems (Chip Huyen)

Weeks 69-72

Read book: Biotechnology Entrepreneurship (Shimasaki)

Comments

Post a Comment

Popular posts from this blog

By
Image
  Project Perseus Introduction Dear reader, Thank you for visiting the Project Perseus blog. I hope that the topics I write about bring you as much joy as they do for me. The world is a wonderful place...if you know where to look. My goal is to help readers reach that place of finding what's wonderful, beautiful, and captivating in this world by giving you a unique perspective and allowing you to take an innocent look at this universe's beauty. But before I begin, I should address some important questions you undoubtedly have: Who are you? My name is Nathaniel Comstock Moll. I am a current student in the fields of biochemistry, molecular biology, and physics. Outside of the technical aspect of my studies I enjoy writing novels, composing original pieces for the piano, doing some amateur backyard astronomy (sometimes volunteering at my school's local observatory), and now apparently writing blog posts. Essentially, I love to learn and to stay curious; two aspects that have c...
Read more

Project Perseus AI ~ Post #1 ~ Machine Learning Origins

By
Image
  Project Perseus AI ~ Post #1 ~ Machine Learning Origins This is the first post in hopefully a series of many that will document my educational journey through the topics of AI and machine learning. Every post will discuss a topic that I've reviewed and/or models that I've programmed to help me better understand these machine learning concepts.  What is the goal with these posts? Again, the goal is to primarily give a record of my self-taught journey in machine learning and to one day create my own AI model which I will name Perseus. I'm quite far away from that point at present, but if I'm diligent enough, I believe I can get there.  I started this journey because I've recognized that the 21st century will most likely be defined as the advent of organic and artificial intelligence cooperation. I believe that a healthy and beneficial cooperation is possible, but that it will require deep understanding on the humans' part and (hopefully) from the AI as well. My ...
Read more

Analyzing DNA-mercury Nanoparticles with Scanning electron Microscopy

By
Image
  Analyzing DNA-mercury Nanoparticles with Scanning electron Microscopy In the last post I discussed how I used fluorometry experiments to investigate the binding dynamics of DNA and mercury ions. In this post, I'm going to talk about how we visualized the DNA - mercury samples via Scanning Electron Microscopy (SEM) to get more information on the structure and morphology of the particles formed by these interactions. As they say, a picture is worth a thousand words! Remember how I said that the DNA forms some kind of hairpin or secondary structure around the mercury ions? Well using SEM we were able to visualize these structures more closely and see how they behave! How did I Prepare the Samples for Visualization? These samples, especially samples containing biological material like DNA, cannot just be thrown into the microscope and visualized. If that happened, the DNA would actually be invisible because of its inability to conduct electrons, since the conductivity of electrons is...
Read more

Learning and Experimenting with Dynamic Light Scattering

By
Image
  Learning and Experimenting with Dynamic Light Scattering This past week at my Ole Miss REU research program has been...interesting to say the least. Not in a bad way, just in a I'm-going-insane-because-all-my-data-is-wacky-no-matter-what-I-do kind of way. The purpose of these experiments that I've been trying to do involves gaining data about the size and distribution of DNA/mercury complexes in solution. I outlined in my first post of this series how Dr. Wadkins has demonstrated that mercury complexes with DNA and induces it to form secondary structures. It's also postulated that these structures can be thought of as fully-fledged nanoparticles.  Dynamic Light Scattering (DLS) is a common way to obtain data about nanoparticles. Therefore, getting usable data from the DLS instrument from my DNA/mercury samples was my first order of business in order to develop an idea of how increased mercury concentrations correlates with particle size in solution. I thought it would be ...
Read more